Navigation auf uzh.ch

Suche

Department of Informatics DDIS

Bachelor/Master Theses and Master Project Topics

This pages lists the open BSc. and MSc. thesis descriptions, as well as the master projects opportunities currently available in the DDIS research group.

If you are interested in any of the listed projects, please do not hesitate to contact the person mentioned in the open topic description.

If there are currently no open topics but you are generally interested in our research (see https://www.ifi.uzh.ch/en/ddis/research.html), or if you would like to propose a thesis about your own idea, you can send us an email to ddis-theses@ifi.uzh.ch.

Master Project: Intelligent Scientific Paper Annotator based on CrowdAlytics Ontology and LLMs

With an overwhelming number of scientific articles available, effective interaction with them is important to facilitate the scientific text understanding. Users will experience a more intuitive way to skim through articles, with important elements like scientific hypotheses, claims, and evidence, instantly highlighted.  

This master project focuses on developing a framework that enhances how users engage with scientific articles in HTML or PDF formats. It leverages our existing CrowdAlytics Annotation Tool, which supports the manual annotation and interaction with hypothesis, and aims to newly integrate advanced pre-trained large language models (LLMs) to automatically identify and highlight key scientific constructs such as hypotheses and/or arguments.  

The project starts with the existing CrowdAlytics Ontology and SciHyp models (pre-trained LLMs), specifically trained for scientific hypotheses identification, and will expand to incorporate various annotation schemas and models as needed. For more information or to discuss this project in detail, please feel free to contact us at the provided email address.

Requirements 2-4 students 

  • With programming skills  

  • Preferably AI students who have knowledge about Semantic Web Technologies and LLMs 

Expected Start date: As soon as possible (expected to finish by summer 2024).

Contact: Rosni Vasu

Master thesis: Dimensionality Reduction for Argumentation Maps

In large-scale deliberations, up to a few thousand people may discuss a topic over a period of time. For newcomers, it then becomes challenging to grasp the state of the debate without reading through all the comments. Machine Learning tools can help mitigate that problem by visualizing opinion maps. Here, groups of users that share certain values are placed close to one another, while users who have different views are placed further away. The goal of this thesis is to explore algorithms that embed users based on their likes and dislikes in a tree-like argumentation map, such as on https://kialo.com

If interested, please get in touch with us at the email address below. We can provide a more detailed description during a meeting. 

Contact: Fynn Bachmann